DeepSeek-OCR 2

deepseek/deepseek-ocr-2

DeepSeek-OCR 2 is a multimodal document recognition model released by DeepSeek AI, serving as an upgrade to DeepSeek-OCR. By introducing the DeepEncoder V2 architecture, it achieves a paradigm shift in visual encoding from "fixed scanning" to "semantic reasoning." The model replaces the original CLIP encoder with a lightweight language model (Qwen2-0.5B) and incorporates a causal flow query mechanism, while retaining the DeepSeek-3B-MoE decoder. The model requires only 256 to 1120 visual tokens to cover complex document pages. On the OmniDocBench v1.5 benchmark, it achieves an overall score of 91.09%, a 3.73% improvement over its predecessor, with reading order recognition edit distance reduced from 0.085 to 0.057.

功能

Serverless API

文档

deepseek/deepseek-ocr-2 is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

可用的 Serverless

立即运行查询，仅按用量付费

输入$0.03 / M Tokens

输出$0.03 / M Tokens

使用以下代码示例与我们的 API 集成：

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="<Your API Key>",
5    base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9    model="deepseek/deepseek-ocr-2",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=8192,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

信息

提供商

DeepSeek

量化

bf16

支持的功能

上下文长度

8192

最大输出

8192

Serverless

支持

输入能力

text, image

输出能力

text

构建生产级 AI 所需的一切。

200+ 个模型、按需 GPUs 和安全的智能体运行时——统一在一个 API 下。免费开始，随业务增长灵活扩展。